Machine Learning Explanations to Prevent Overtrust in Fake News Detection

07/24/2020
by   Sina Mohseni, et al.
16

Combating fake news and misinformation propagation is a challenging task in the post-truth era. News feed and search algorithms could potentially lead to unintentional large-scale propagation of false and fabricated information with users being exposed to algorithmically selected false content. Our research investigates the effects of an Explainable AI assistant embedded in news review platforms for combating the propagation of fake news. We design a news reviewing and sharing interface, create a dataset of news stories, and train four interpretable fake news detection algorithms to study the effects of algorithmic transparency on end-users. We present evaluation results and analysis from multiple controlled crowdsourced studies. For a deeper understanding of Explainable AI systems, we discuss interactions between user engagement, mental model, trust, and performance measures in the process of explaining. The study results indicate that explanations helped participants to build appropriate mental models of the intelligent assistants in different conditions and adjust their trust accordingly for model limitations.

READ FULL TEXT
research
07/23/2022

Towards Smart Fake News Detection Through Explainable AI

People now see social media sites as their sole source of information du...
research
12/07/2021

Do explanations increase the effectiveness of AI-crowd generated fake news warnings?

Social media platforms are increasingly deploying complex interventions ...
research
04/04/2019

Open Issues in Combating Fake News: Interpretability as an Opportunity

Combating fake news needs a variety of defense methods. Although rumor d...
research
04/17/2023

User Perceptions of Automatic Fake News Detection: Can Algorithms Fight Online Misinformation?

Fake news detection algorithms apply machine learning to various news at...
research
11/29/2018

Combating Fake News with Interpretable News Feed Algorithms

Nowadays, artificial intelligence algorithms are used for targeted and p...
research
07/08/2019

XFake: Explainable Fake News Detector with Visualizations

In this demo paper, we present the XFake system, an explainable fake new...
research
09/02/2020

Micro-entries: Encouraging Deeper Evaluation of Mental Models Over Time for Interactive Data Systems

Many interactive data systems combine visual representations of data wit...

Please sign up or login with your details

Forgot password? Click here to reset